© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 2-RES-SM
    11. 26575
    Prev
    Next
    INDEX
    Explanations

    phrases relating to scientific studies or evaluations of medical conditions and their impacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__res-sm_processed/2-res-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    156
    +0.21
    1.2%
    240
    +0.15
    0.9%
    186
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    418
    +0.21
    -0.02
    304
    +0.15
    0.08
    240
    +0.13
    -0.02
    Negative Logits
    gio
    -1.47
    fileID
    -1.46
    writers
    -1.45
     eukary
    -1.45
    serif
    -1.42
    ascii
    -1.39
    fected
    -1.38
    writer
    -1.38
    drive
    -1.37
    held
    -1.35
    POSITIVE LOGITS
    ĻĤ
    3.99
    Ĥ¬
    3.78
    ĨĴ
    3.71
    »
    3.63
    ²
    3.42
    ³
    3.40
    ¿½
    3.39
    ¹
    3.36
    3.35
    3.35
    Activations Density 1.840%

    No Known Activations